Today, we send operations in phase2 of peer recoveries batch by batch
sequentially. Normally that's okay as we should have a fairly small of
operations in phase 2 due to the file-based threshold. However, if
phase1 takes a lot of time and we are actively indexing, then phase2 can
have a lot of operations to replay.
With this change, we will send multiple batches concurrently (defaults
to 1) to reduce the recovery time.
Backport of #58018
* Adding ESS icons to supported ES settings.
* Adding new file for supported ESS settings.
* Adding supported ESS settings for HTTP and disk-based shard allocation.
* Adding more supported settings for ESS.
* Adding descriptions for each Cloud section, plus additional settings.
* Adding new warehouse file for Cloud, plus additional settings.
* Adding node settings for Cloud.
* Adding audit settings for Cloud.
* Resolving merge conflict.
* Adding SAML settings (part 1).
* Adding SAML realm encryption and signing settings.
* Adding SAML SSL settings.
* Adding Kerberos realm settings.
* Adding OpenID Connect Realm settings.
* Adding OpenID Connect SSL settings.
* Resolving leftover Git merge markers.
* Removing Cloud settings page and link to it.
* Add link to mapping source
* Update docs/reference/docs/reindex.asciidoc
* Incorporate edit of HTTP settings
* Remove "cloud" from tag and ID
* Remove "cloud" from tag and update description
* Remove "cloud" from tag and ID
* Change "whitelists" to "specifies"
* Remove "cloud" from end tag
* Removing cloud from IDs and tags.
* Changing link reference to fix build issue.
* Adding index management page for missing settings.
* Removing warehouse file for Cloud and moving settings elsewhere.
* Clarifying true/false usage of http.detailed_errors.enabled.
* Changing underscore to dash in link to fix ci build.
Restoring from a snapshot (which is a particular form of recovery) does not currently take recovery throttling into account
(i.e. the `indices.recovery.max_bytes_per_sec` setting). While restores are subject to their own throttling (repository
setting `max_restore_bytes_per_sec`), this repository setting does not allow for values to be configured differently on a
per-node basis. As restores are very similar in nature to peer recoveries (streaming bytes to the node), it makes sense to
configure throttling in a single place.
The `max_restore_bytes_per_sec` setting is also changed to default to unlimited now, whereas previously it was set to
`40mb`, which is the current default of `indices.recovery.max_bytes_per_sec`). This means that no behavioral change
will be observed by clusters where the recovery and restore settings were not adapted.
Relates https://github.com/elastic/elasticsearch/issues/57023
Co-authored-by: James Rodewig <james.rodewig@elastic.co>
The `indices.recovery.max_bytes_per_sec` recovery bandwidth limit can differ
between nodes if it is not set dynamically, but today this is not obvious. This
commit adds a paragraph to its documentation clarifying how to set different
bandwidth limits on each node.
Co-Authored-By: James Rodewig <james.rodewig@elastic.co>
Most of the circuit breaker settings are dynamically configurable.
However, `indices.breaker.total.use_real_memory` is not. With this
commit we add a clarifying note that this specific setting is static.
Closes#44974
* Clarify that peer recovery settings apply to shard relocation
* Fix awkward wording of 1st sentence
* [DOCS] Remove snapshot recovery reference.
Call out link to [[cat-recovery]].
Separate expert settings.
The "include_type_name" parameter was temporarily introduced in #37285 to facilitate
moving the default parameter setting to "false" in many places in the documentation
code snippets. Most of the places can simply be reverted without causing errors.
In this change I looked for asciidoc files that contained the
"include_type_name=true" addition when creating new indices but didn't look
likey they made use of the "_doc" type for mappings. This is mostly the case
e.g. in the analysis docs where index creating often only contains settings. I
manually corrected the use of types in some places where the docs still used an
explicit type name and not the dummy "_doc" type.
* Default include_type_name to false for get and put mappings.
* Default include_type_name to false for get field mappings.
* Add a constant for the default include_type_name value.
* Default include_type_name to false for get and put index templates.
* Default include_type_name to false for create index.
* Update create index calls in REST documentation to use include_type_name=true.
* Some minor clean-ups around the get index API.
* In REST tests, use include_type_name=true by default for index creation.
* Make sure to use 'expression == false'.
* Clarify the different IndexTemplateMetaData toXContent methods.
* Fix FullClusterRestartIT#testSnapshotRestore.
* Fix the ml_anomalies_default_mappings test.
* Fix GetFieldMappingsResponseTests and GetIndexTemplateResponseTests.
We make sure to specify include_type_name=true during xContent parsing,
so we continue to test the legacy typed responses. XContent generation
for the typeless responses is currently only covered by REST tests,
but we will be adding unit test coverage for these as we implement
each typeless API in the Java HLRC.
This commit also refactors GetMappingsResponse to follow the same appraoch
as the other mappings-related responses, where we read include_type_name
out of the xContent params, instead of creating a second toXContent method.
This gives better consistency in the response parsing code.
* Fix more REST tests.
* Improve some wording in the create index documentation.
* Add a note about types removal in the create index docs.
* Fix SmokeTestMonitoringWithSecurityIT#testHTTPExporterWithSSL.
* Make sure to mention include_type_name in the REST docs for affected APIs.
* Make sure to use 'expression == false' in FullClusterRestartIT.
* Mention include_type_name in the REST templates docs.
Today file-chunks are sent sequentially one by one in peer-recovery. This is a
correct choice since the implementation is straightforward and recovery is
network bound in most of the time. However, if the connection is encrypted, we
might not be able to saturate the network pipe because encrypting/decrypting
are cpu bound rather than network-bound.
With this commit, a source node can send multiple (default to 2) file-chunks
without waiting for the acknowledgments from the target.
Below are the benchmark results for PMC and NYC_taxis.
- PMC (20.2 GB)
| Transport | Baseline | chunks=1 | chunks=2 | chunks=3 | chunks=4 |
| ----------| ---------| -------- | -------- | -------- | -------- |
| Plain | 184s | 137s | 106s | 105s | 106s |
| TLS | 346s | 294s | 176s | 153s | 117s |
| Compress | 1556s | 1407s | 1193s | 1183s | 1211s |
- NYC_Taxis (38.6GB)
| Transport | Baseline | chunks=1 | chunks=2 | chunks=3 | chunks=4 |
| ----------| ---------| ---------| ---------| ---------| -------- |
| Plain | 321s | 249s | 191s | * | * |
| TLS | 618s | 539s | 323s | 290s | 213s |
| Compress | 2622s | 2421s | 2018s | 2029s | n/a |
Relates #33844
* Lower fielddata circuit breaker default limit
Lower fielddata circuit breaker default limit from 60% to 40% as we have
moved to doc_values for most of the cases.
* merge master in
* update tests
* update docs
This change adds a section about the global search setting
`indices.query.bool.max_clause_count` that limits the number of boolean clauses
allowed in a Lucene BooleanQuery.
Closes#19858
With this commit we introduce a new circuit-breaking strategy to the parent
circuit breaker. Contrary to the current implementation which only accounts for
memory reserved via child circuit breakers, the new strategy measures real heap
memory usage at the time of reservation. This allows us to be much more
aggressive with the circuit breaker limit so we bump it to 95% by default. The
new strategy is turned on by default and can be controlled with the new cluster
setting `indices.breaker.total.userealmemory`.
Note that we turn it off for all integration tests with an internal test cluster
because it leads to spurious test failures which are of no value (we cannot
fully control heap memory usage in tests). All REST tests, however, will make
use of the real memory circuit breaker.
Relates #31767
So far the in-flight request circuit breaker has only accounted for the
on-the-wire representation of a request. However, we convert the raw
request into XContent internally which increases the overhead.
Therefore, we increase the value of the corresponding setting
`network.breaker.inflight_requests.overhead` from one to two. While this
value is still rather conservative (we assume that the representation as
structured objects has no overhead compared to the byte[]), it is closer
to reality than the current value.
Relates #31613
The documentation for the account circuit breaker listed the settings for it's limit and overhead to be `network.breaker.accounting.limit` and `network.breaker.accounting.overhead` when in `HieratchyCircuitBreakerService` it seems the settings are actually `indices.breaker.accounting.limit` and `indices.breaker.accounting.overhead`.
* Add accounting circuit breaker and track segment memory usage
This commit adds a new circuit breaker "accounting" that is used for tracking
the memory usage of non-request-tied memory users. It also adds tracking for the
amount of Lucene segment memory used by a shard as a user of the new circuit
breaker.
The Lucene segment memory is updated when the shard refreshes, and removed when
the shard relocates away from a node or is deleted. It should also be noted that
all tracking for segment memory uses `addWithoutBreaking` so as not to fail the
shard if a limit is reached.
The `accounting` breaker has a default limit of 100% and will contribute to the
parent breaker limit.
Resolves#27044
The current script service has a script compilation limit for a one
minute window. This is set to a small default value of 15. Instead of
increasing that default value, this commit introduces a new setting
that allows to configure a rate per time unit, so that the script service can deal with bursts better.
The new setting is named `script.max_compilations_rate`,
requires a nonnegative number and a positive time value.
The default is `75/5m`, which is equivalent to the existing 15 per minute.
* plugins/discovery-azure-class.asciidoc
* reference/cluster.asciidoc
* reference/modules/cluster/misc.asciidoc
* reference/modules/indices/request_cache.asciidoc
After this is merged there will be no unconvereted snippets outside
of `reference`.
Related to #18160
When compiling many dynamically changing scripts, parameterized
scripts (<https://www.elastic.co/guide/en/elasticsearch/reference/master/modules-scripting-using.html#prefer-params>)
should be preferred. This enforces a limit to the number of scripts that
can be compiled within a minute. A new dynamic setting is added -
`script.max_compilations_per_minute`, which defaults to 15.
If more dynamic scripts are sent, a user will get the following
exception:
```json
{
"error" : {
"root_cause" : [
{
"type" : "circuit_breaking_exception",
"reason" : "[script] Too many dynamic script compilations within one minute, max: [15/min]; please use on-disk, indexed, or scripts with parameters instead",
"bytes_wanted" : 0,
"bytes_limit" : 0
}
],
"type" : "search_phase_execution_exception",
"reason" : "all shards failed",
"phase" : "query",
"grouped" : true,
"failed_shards" : [
{
"shard" : 0,
"index" : "i",
"node" : "a5V1eXcZRYiIk8lecjZ4Jw",
"reason" : {
"type" : "general_script_exception",
"reason" : "Failed to compile inline script [\"aaaaaaaaaaaaaaaa\"] using lang [painless]",
"caused_by" : {
"type" : "circuit_breaking_exception",
"reason" : "[script] Too many dynamic script compilations within one minute, max: [15/min]; please use on-disk, indexed, or scripts with parameters instead",
"bytes_wanted" : 0,
"bytes_limit" : 0
}
}
}
],
"caused_by" : {
"type" : "general_script_exception",
"reason" : "Failed to compile inline script [\"aaaaaaaaaaaaaaaa\"] using lang [painless]",
"caused_by" : {
"type" : "circuit_breaking_exception",
"reason" : "[script] Too many dynamic script compilations within one minute, max: [15/min]; please use on-disk, indexed, or scripts with parameters instead",
"bytes_wanted" : 0,
"bytes_limit" : 0
}
}
},
"status" : 500
}
```
This also fixes a bug in `ScriptService` where requests being executed
concurrently on a single node could cause a script to be compiled
multiple times (many in the case of a powerful node with many shards)
due to no synchronization between checking the cache and compiling the
script. There is now synchronization so that a script being compiled
will only be compiled once regardless of the number of concurrent
searches on a node.
Relates to #19396
This adds new circuit breaking with the "request" breaker, which adds
circuit breaks based on the number of buckets created during
aggregations. It consists of incrementing during AggregatorBase creation
This also bumps the REQUEST breaker to 60% of the JVM heap now.
The output when circuit breaking an aggregation looks like:
```json
{
"shard" : 0,
"index" : "i",
"node" : "a5AvjUn_TKeTNYl0FyBW2g",
"reason" : {
"type" : "exception",
"reason" : "java.util.concurrent.ExecutionException: QueryPhaseExecutionException[Query Failed [Failed to execute main query]]; nested: CircuitBreakingException[[request] Data too large, data for [<agg [otherthings]>] would be larger than limit of [104857600/100mb]];",
"caused_by" : {
"type" : "execution_exception",
"reason" : "QueryPhaseExecutionException[Query Failed [Failed to execute main query]]; nested: CircuitBreakingException[[request] Data too large, data for [<agg [myagg]>] would be larger than limit of [104857600/100mb]];",
"caused_by" : {
"type" : "circuit_breaking_exception",
"reason" : "[request] Data too large, data for [<agg [otherthings]>] would be larger than limit of [104857600/100mb]",
"bytes_wanted" : 104860781,
"bytes_limit" : 104857600
}
}
}
}
```
Relates to #14046
Previously if the size of the search request was greater than zero we would not cache the request in the request cache.
This change retains the default behaviour of not caching requests with size > 0 but also allows the `request_cache=true` query parameter
to enable the cache for requests with size > 0
With this commit we limit the size of all in-flight requests on
transport level. The size is guarded by a circuit breaker and is
based on the content size of each request.
By default we use 100% of available heap meaning that the parent
circuit breaker will limit the maximum available size. This value
can be changed by adjusting the setting
network.breaker.inflight_requests.limit
Relates #16011
Today we throttle recoveries only for incoming recoveries. Nodes that have a lot
of primaries can get overloaded due to too many recoveries. To still keep that at bay
we limit the number of threads that are sending files to the target to overcome this problem.
The right solution here is to also throttle the outgoing recoveries that are today unbounded on
the master and don't start the recovery until we have enough resources on both source and target nodes.
The concurrency aspects of the recovery source also added a lot of complexity and additional threadpools
that are hard to configure. This commit removes the concurrent streamns notion completely and sends files
in the thread that drives the recovery simplifying the recovery code considerably.
Outgoing recoveries are not throttled on the master via a allocation decider.
James Rodewig
Nhat Nguyen
Adam Locke
Yannick Welsch
Stuart Tettemer
James Rodewig
David Turner
István Zoltán Szabó
Patryk Krawaczyński
Daniel Mitterdorfer
Sam Mingo
Christoph Büscher
Julie Tibshirani
Yu
Alexandru Rusanescu
Daniel Mitterdorfer
Colin Goodheart-Smithe
Lee Jones
Lee Hinman
Alexander Reelsen
Robin Clarke
Stefan Gorgiovski
alamzeeshan
Nik Everett
Lee Hinman
Adrien Grand
Michael McCandless
Simon Willnauer